Borrowing it
Nothing to install: this file belongs to dannyota/banhmi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dannyota/banhmi/master/CLAUDE.mdgit clone --depth 1 https://github.com/dannyota/banhmiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/dannyota/banhmi/claude-md)<a href="https://agentmods.dev/instructions/dannyota/banhmi/claude-md"><img src="https://agentmods.dev/badge/instructions/dannyota/banhmi/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/dannyota/banhmi/claude-md"><img src="https://agentmods.dev/badge/instructions/dannyota/banhmi/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00476 | $0.00476 |
| Opus 5.5 | $0.00190 | $0.00190 |
| Sonnet 5.5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
banhmi CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
@AGENTS.md
Use .claude/agents/designer.md for Claude design and research.
For Codex jobs, resolve CODEX_COMPANION to the newest installed Codex plugin, never a pinned
version path:
CODEX_COMPANION="$(ls -d ~/.claude/plugins/cache/openai-codex/codex/*/ | sort -V | tail -1)scripts/codex-companion.mjs"
From the worktree that owns the job, run:
node "$CODEX_COMPANION" task --background [--write] --fresh --model <model> --effort <effort> "<prompt>"
node "$CODEX_COMPANION" status <job-id>
node "$CODEX_COMPANION" result <job-id>
The brackets mark an optional flag, not literal command text.
Use --write only for a job authorized to edit its owned files.
Run status and result from the same directory as task.
Start fix passes with --fresh and a full brief. --resume-last resumes the most recent
job in that directory, which may be a different role's thread.
Wait for a job in a background loop that polls status <job-id> --json no more often than every
90 seconds and stops when the job is completed, failed, cancelled, or missing.
Use the role, model, effort, and review isolation required by AGENTS.md.
GitHub evidence and landing:
gh pr checks <pr> # required check is `CI`
gh run view <run-id> --log-failed # error lines for a troubleshooter brief
gh run download <run-id> -n <artifact> -D <dir> # generation artifacts; review before import
gh api -X DELETE notifications/threads/<id> # mark a handled notification done
Review a generation artifact under verification and
engineering rules before import. For a formatting-only patch,
every changed Go file must match its committed version once whitespace and the statement-separating
semicolons gofmt drops are removed; review every module change.
Answer each review thread, then resolve it; the master ruleset blocks merge while a thread is open.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago Changed · +1 lines · +10 tokens per session 1b1300914d23
- 26d ago First seen · 35 lines · 466 tokens per session scan A 9d75bb9fe9a3
banhmi CLAUDE.md is an instructions file published in the GitHub repository dannyota/banhmi (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 476 tokens to every session, about $0.0019 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-12.
banhmi CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| banhmi CLAUDE.mddannyota/banhmi | Instructions file | 2 | 6d ago | Apache-2.0 | A | 476 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |